hebrew-chatbot-builder

A guide for building chatbots that understand and respond in Hebrew across WhatsApp, Telegram, and websites. It also covers right-to-left display, Hebrew wording, and conversation flows.

In plain words
What is it for?
Create a Hebrew bot for WhatsApp, Telegram, or a web chat widget, including its message handling, response wording, right-to-left interface, and conversation structure.
Why use it?
Hebrew chatbots can display text in the wrong direction, use unsuitable formalities or gendered wording, and split Hebrew text incorrectly. This guide addresses those language and interface problems.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/squadcodercom/squadcoder/hebrew-chatbot-builder
Any agent
npx skills add squadcodercom/squadcoder --skill hebrew-chatbot-builder
Clone the repo
git clone --depth 1 https://github.com/squadcodercom/squadcoder

Made for: Claude Code, Codex.

Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00212 $0.09620
Opus 5 $0.00106 $0.04810
Sonnet 5 $0.00042 $0.01924
Haiku 4.5 $0.00021 $0.00962

Measured 2d ago against content hash d84ccab0a6ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hebrew-chatbot-builder scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/telegram-bot-scaffold.py, scripts/whatsapp-webhook-handler.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

response = requests.post(url, json=payload, headers=headers)
.squadcoder/skills/hebrew-chatbot-builder/SKILL.md · 989 lines

How it starts

The opening of the file, as written. The whole thing — 989 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hebrew Chatbot Builder

Build production-ready conversational AI chatbots with native Hebrew support. This skill covers platform integrations (WhatsApp, Telegram, web), Hebrew language patterns, RTL UI components, and conversation flow design for Hebrew speakers.

Instructions

Follow this procedure when building a Hebrew chatbot:

  1. Identify the platform/channel. Confirm whether the bot runs on WhatsApp Business API, Telegram, an embedded web widget, or several at once. Each has a different scaffold and message model.
  2. Confirm formal or informal register. Ask the user whether the audience expects informal Hebrew ("דוגרי", recommended for most consumer bots) or formal Hebrew (government, banking, legal). This decision shapes every response string.
  3. Ask the gender-handling strategy. Decide between asking the user's gender early and remembering it, using gender-neutral phrasing throughout, or slash notation ("את/ה"). See the Gender-Aware Responses section.
  4. Scaffold via the relevant bundled script. Use scripts/whatsapp-webhook-handler.py for WhatsApp or scripts/telegram-bot-scaffold.py for Telegram as the starting point, then adapt the Hebrew response templates and conversation flows.
  5. Wire entity extraction. Add extract_israeli_entities() (or an equivalent) so the bot recognizes Israeli phone numbers, NIS amounts, dates, and Teudat Zehut from free-text Hebrew input.
  6. Verify RTL rendering. For web widgets, set dir="rtl" on the outermost container and test on a real device. For WhatsApp and Telegram, verify Hebrew text and interactive buttons render correctly on both iOS and Android.

Examples

Example 1: WhatsApp order-status bot in Hebrew

User says: "Build a WhatsApp bot in Hebrew that lets customers check their order status."

Actions:

  1. Identify the channel: WhatsApp Business Cloud API.
  2. Confirm informal register (consumer audience) and gender-neutral phrasing for broad reach.
  3. Start from scripts/whatsapp-webhook-handler.py, which already includes webhook verification, signature checks, and Hebrew response templates.
  4. Wire an interactive button menu ("בדיקת הזמנה", "שאלות נפוצות", "דבר/י עם נציג") and a waiting_order_number state that validates the order number and looks it up.
  5. Submit a Hebrew order_confirmation_he template via Meta Business Suite for proactive outbound updates.

Read the full file on GitHub · 989 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 989 lines · 212 tokens per session scan A d84ccab0a6ec

Subscribe to this mod's changes

hebrew-chatbot-builder is a skill published in the GitHub repository squadcodercom/squadcoder (11 stars, last pushed 2mo ago), licensed MIT. It adds 212 tokens to every session and 9,620 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

write-zot-themes

Help the user create, install, or package zot themes, including theme-only extensions.

patriceckhart/zot · 23 tokens

python-testing

Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization. Use when writing or improving Python tests.

mturac/everything-openai-codex · 35 tokens

database-migrations

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Django, TypeORM, golang-migrate). Use when planning or implementing database schema changes.

mturac/everything-openai-codex · 61 tokens

docker-patterns

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Use when setting up containerized development environments or reviewing Docker configurations.

mturac/everything-openai-codex · 40 tokens

python-patterns

Python-specific design patterns and best practices including protocols, dataclasses, context managers, decorators, async/await, type hints, and package organization. Use when working with Python code to apply Pythonic patterns.

mturac/everything-openai-codex · 45 tokens

st-full-workflow

Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or…

e0ipso/strikethroo · 90 tokens